arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01100cs.LGcs.CR
收藏

针对图神经网络的群属性推断攻击

Group Property Inference Attacks Against Graph Neural Networks

Stevens Institute of Technology(史蒂文斯理工学院)

Xiuling Wang, Wendy Hui Wang

摘要:

随着机器学习(ML)技术的快速采用,ML模型的共享变得流行。然而,ML模型容易受到隐私攻击,泄露有关训练数据的信息。在这项工作中,我们专注于一种特殊类型的隐私攻击,称为属性推理攻击(PIA),它通过访问目标ML模型来推断训练数据的敏感属性。特别地,我们将图神经网络(GNNs)视为目标模型,并将训练图中特定节点和链接组的分布视为目标属性。虽然现有的工作已经研究了PIA,目标在图级的属性,没有以前的工作已经研究了推理的节点和链接属性在组的水平。在这项工作中,我们首次系统地研究了针对GNN的群属性推断攻击(GPIA)。首先,我们考虑黑盒和白盒设置下的威胁模型的分类与各种类型的对手的知识,并设计六种不同的攻击这些设置。我们通过对三个代表性的GNN模型和三个真实世界的图进行广泛的实验来评估这些攻击的有效性。我们的研究结果表明,这些攻击的准确性优于基线方法的有效性。其次,我们分析了GPIA成功的潜在因素,并表明在具有或不具有目标属性的图上训练的目标模型在模型参数和/或模型输出中表现出一些不同,这使得对手能够推断出属性的存在。此外,我们还设计了一套针对GPIA攻击的防御机制,并证明了这些机制可以有效地降低攻击精度,而GNN模型的精度损失很小。

英文摘要:

With the fast adoption of machine learning (ML) techniques, sharing of ML models is becoming popular. However, ML models are vulnerable to privacy attacks that leak information about the training data. In this work, we focus on a particular type of privacy attacks named property inference attack (PIA) which infers the sensitive properties of the training data through the access to the target ML model. In particular, we consider Graph Neural Networks (GNNs) as the target model, and distribution of particular groups of nodes and links in the training graph as the target property. While the existing work has investigated PIAs that target at graph-level properties, no prior works have studied the inference of node and link properties at group level yet. In this work, we perform the first systematic study of group property inference attacks (GPIA) against GNNs. First, we consider a taxonomy of threat models under both black-box and white-box settings with various types of adversary knowledge, and design six different attacks for these settings. We evaluate the effectiveness of these attacks through extensive experiments on three representative GNN models and three real-world graphs. Our results demonstrate the effectiveness of these attacks whose accuracy outperforms the baseline approaches. Second, we analyze the underlying factors that contribute to GPIA's success, and show that the target model trained on the graphs with or without the target property represents some dissimilarity in model parameters and/or model outputs, which enables the adversary to infer the existence of the property. Further, we design a set of defense mechanisms against the GPIA attacks, and demonstrate that these mechanisms can reduce attack accuracy effectively with small loss on GNN model accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑